Open LiTian0215 opened 1 year ago
Hi, The camera parameters are fixed in world space, but there is a head pose transformation for each frame. In other words, in world space, the camera parameters are fixed across the sequence. But the camera parameters have different model space coordinates in each frame due to the head pose transformation (the head pose is called "modelmatrix" in multiviewvideo.py).
Hi, I noticed that the multi-view images of different frames of the same expression with the same id in your dataset have fixed camera parameters when reconstructing the mesh. When I try to perform mesh reconstruction from multi-view images, the camera parameters obtained from multi-view image reconstruction from different frames are all different. I was wondering how you fixed the camera parameters for mesh reconstruction.